Agent skills for ChatGPT

Implement a task with automated LLM-as-Judge verification for critical steps

Generates granular, step-by-step implementation plans for complex coding tasks using TDD and micro-commit principles.

Convert implementation plan into discrete, executable tickets for Claude Code

John Carmack-level implementation review via rp-cli for current branch changes.

Use `LayoutBuilder`, `MediaQuery`, or `Expanded/Flexible` to create a layout that adapts to different screen sizes.

Use this skill whenever you are implementing or fixing an update_* tool in unifi-mcp.

Deploy AWS Security Hub as a centralized CSPM platform, backed by AWS

Implement and extend PostHog Data warehouse import sources.

Implements Delinea Secret Server for privileged access management,

Use the `http` package to execute GET, POST, PUT, or DELETE requests.

Implements JavaScript classes in C++ using JavaScriptCore.

Write custom Semgrep SAST rules in YAML to detect application-specific

Runs an AI code review of a change and records each finding as an open item in a code-review session record.

Imports existing Grafana dashboards as Go builder code via gcx.

Imports GitHub PR review comments as open items in a code-review session record, keeping the comment id, author, inline location, thread…

Starts from visual examples supplied by the user (a logo, screenshots of their site, existing visuals, an image they like, a moodboard) to…

Analyze development-set disagreements between human annotations and one Coval text LLM judge, then propose a focused prompt revision.

Audit any Hermes agent setup — crons, profiles, A2A meshes, workflows — and propose improvements in a visual HTML report.

Analyze and improve existing documentation using Diataxis principles

Audit and modernize Node.js scripts inside portable skills with explicit dependencies, committed lockfiles, local npm commands, compiled…

Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained…